metadata
license: afl-3.0
base_model: Davlan/bert-base-multilingual-cased-ner-hrl
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: belajarner_bert_case
results: []
belajarner_bert_case
This model is a fine-tuned version of Davlan/bert-base-multilingual-cased-ner-hrl on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3309
- Precision: 0.8120
- Recall: 0.8430
- F1: 0.8272
- Accuracy: 0.9423
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2528 | 1.0 | 1567 | 0.2352 | 0.7442 | 0.8116 | 0.7765 | 0.9282 |
| 0.1653 | 2.0 | 3134 | 0.2250 | 0.8008 | 0.8218 | 0.8112 | 0.9378 |
| 0.1125 | 3.0 | 4701 | 0.2545 | 0.7703 | 0.8381 | 0.8028 | 0.9343 |
| 0.083 | 4.0 | 6268 | 0.2633 | 0.8065 | 0.8353 | 0.8206 | 0.9401 |
| 0.0602 | 5.0 | 7835 | 0.2860 | 0.8124 | 0.8229 | 0.8176 | 0.9413 |
| 0.0411 | 6.0 | 9402 | 0.3129 | 0.8026 | 0.8353 | 0.8186 | 0.9404 |
| 0.0324 | 7.0 | 10969 | 0.3180 | 0.8036 | 0.8400 | 0.8214 | 0.9418 |
| 0.0248 | 8.0 | 12536 | 0.3309 | 0.8120 | 0.8430 | 0.8272 | 0.9423 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2